© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8267
    Prev
    Next
    INDEX
    Explanations

    words related to quantities and measurements, often in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Consultative
    -0.39
    contentLoaded
    -0.38
    JsonValue
    -0.35
    󠁬
    -0.35
    IMPORTED
    -0.35
    "__
    -0.34
     couper
    -0.32
    łecz
    -0.32
    icylic
    -0.31
     UIAlert
    -0.30
    POSITIVE LOGITS
     sixties
    0.81
     fifties
    0.79
     thirties
    0.78
     twenties
    0.78
     decade
    0.77
     seventies
    0.77
     decades
    0.76
     década
    0.76
     forties
    0.75
     eighties
    0.73
    Activations Density 0.114%

    No Known Activations